OpenAI introduces Sora

[bnew]

Spoiler: thread continued

Spoiler: full text & large images

1/11
@runwayml
Introducing, Act-One. A new way to generate expressive character performances inside Gen-3 Alpha using a single driving video and character image. No motion capture or rigging required.

Learn more about Act-One below.

(1/7)



https://video-t-2.twimg.com/ext_tw_...248/pu/vid/avc1/1280x720/2EyYj6GjSpT_loQf.mp4

2/11
@runwayml
Act-One allows you to faithfully capture the essence of an actor's performance and transpose it to your generation. Where traditional pipelines for facial animation involve complex, multi-step workflows, Act-One works with a single driving video that can be shot on something as simple as a cell phone.

(2/7)



https://video-t-2.twimg.com/ext_tw_...282/pu/vid/avc1/1280x720/Qie29gOWU42zMaGo.mp4

3/11
@runwayml
Without the need for motion-capture or character rigging, Act-One is able to translate the performance from a single input video across countless different character designs and in many different styles.

(3/7)



https://video-t-2.twimg.com/ext_tw_...696/pu/vid/avc1/1280x720/TcWzpRl3kMfHM4ro.mp4

4/11
@runwayml
One of the models strengths is producing cinematic and realistic outputs across a robust number of camera angles and focal lengths. Allowing you generate emotional performances with previously impossible character depth opening new avenues for creative expression.

(4/7)



https://video-t-2.twimg.com/ext_tw_...424/pu/vid/avc1/1280x720/3fupOI32Ck6ITIiE.mp4

5/11
@runwayml
A single video of an actor is used to animate a generated character.

(5/7)



https://video-t-2.twimg.com/ext_tw_...016/pu/vid/avc1/1280x720/Fh7WanCgSTR_ffHF.mp4

6/11
@runwayml
With Act-One, eye-lines, micro expressions, pacing and delivery are all faithfully represented in the final generated output.

(6/7)



https://video-t-2.twimg.com/ext_tw_...528/pu/vid/avc1/1280x720/ywweYvzLHe-3GO2B.mp4

7/11
@runwayml
Access to Act-One will begin gradually rolling out to users today and will soon be available to everyone.

To learn more, visit Runway Research | Introducing Act-One

(7/7)



8/11
@xushanpao310
@threadreaderapp Unroll



9/11
@threadreaderapp
@xushanpao310 Salam, please find the unroll here: Thread by @runwayml on Thread Reader App See you soon.



10/11
@threadreaderapp
Your thread is gaining traction! /search?q=#TopUnroll Thread by @runwayml on Thread Reader App @TheReal_Ingrid_ for unroll



11/11
@flowersslop
motion capture industry is cooked




To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196

 

[bnew]

Spoiler: full text & large images

1/70
@RuudNL
Sora v2 release is impending:

* 1-minute video outputs
* text-to-video
* text+image-to-video
* text+video-to-video

OpenAI's Chad Nelson showed this at the C21Media Keynote in London. And he said we will see it very very soon, as @sama has foreshadowed.



https://video.twimg.com/ext_tw_video/1865424798098063360/pu/vid/avc1/1280x720/o2CgvaQxW-BwzuLv.mp4

2/70
@crownut984
Bro no one has access to to v1 why should I care about v2



3/70
@AI_Car_Pool
Monday - noon EST - 200$ per plan



4/70
@MicahJanke
Here’s to hoping the price isn’t insane



5/70
@caojiaming1
Looking forward to it!



6/70
@Goran_Majic
Put all the OpenAI employees in a room with all the computing power in the world, but no access to the internet and anyone else's content. Let them rebuild from scratch. It might be interesting to see what that would look like.



7/70
@clay_ripma
The convergence of this + VR is going to open up an entirely new category of personalized entertainment.

Most big releases are already 2 hours of CGI with a thin plot. Yawn.

But put me in there in VR where I can change around the story? It’ll be like lucid dreaming. I’m in.



8/70
@Nexus_AiAcademy
this is wild



9/70
@majdoubTn
Definitely need this



10/70
@TB_Motion
Holy s... I need more storage space



11/70
@pratjoey
Text and image to video will be a rich area.



12/70
@LittleTinRobot
I remain optimistic as have been waiting around this tech for a while now to test it out.
All sounds very intriguing.



13/70
@creativstrm
so there was a Sora V1? probably in another dimension... and even if a sora v2 will exist, it will be for professional users. So, whatever.



14/70
@boneGPT
big



15/70
@MaxZiebell
This is impressive—when is this from? Either it’s highly cherry-picked, or they’ve been hard at work. I had written off Sora as being overtaken, but could this mark a major comeback?



16/70
@TheAI_Frontier
It will be on day 3, I can feel it.



17/70
@koltregaskes
Looks great but I'm wondering release to who? Hollywood only?



18/70
@ZMadoc
Can’t wait!



19/70
@StevieMac03
V2? What happened to v1?



20/70
@jphilipp
Here's hoping for them to eventually release a lipsync tool, too... we need higher-quality and more face-detecting ones.



21/70
@MotionMark1111
Whoa



22/70
@rchitectopteryx
Where is v1?



23/70
@BenPielstick
If we can get 1 minute continuous shots and consistent characters between shots we are going to have a very interesting year.



24/70
@U79916881747113
Thats a big screen and the quality looks highly impressive so it must be 1080p or may be 2K and also the frame rate seems to be high so may be 24fps



25/70
@PlutusCosmos
Looking forward to it!



26/70
@iamdeepaklenka
Wow,it’s just incredible



27/70
@thegenioo
stunning and amazing



28/70
@imagineadil
wow



29/70
@PJaccetturo
Now I’m hyped.



30/70
@Emily_Escapor
I am ready the prompt is ready



31/70
@azed_ai
Wild!



32/70
@edalgomezn
@nicdunz



33/70
@bilawalsidhu
Okay this has me hyped — the military characters and spaceship generations are right up my alley



34/70
@NeuralHours
Incredible



35/70
@AliceAI314
I genuinely can't wait to get my hands on that. Look at the face consistency where the blood is splattered on her nose. It's identical to the other shot. Sora is looking stunning. And the biggest thing for me is little to no morphing and consistent characters.



36/70
@Yang_ML_Estate
Currently I have been using Kling. Will try Sora v2 after its release



37/70
@nebsh83
Bet they will drop it for xmas



38/70
@ChukwumaNwaugha
Wow, this is super impressive.



39/70
@mark_k
Very cool, thanks for posting!



40/70
@techguyver
What about API availability?



41/70
@Marconium2
What do you mean v2? We never got to see v1 lol



42/70
@DreschHorbach
Will it be pro only?



43/70
@Eric520CC
Amazing, very much looking forward to SORA V2, will it be released tomorrow?



44/70
@rajeshkannan_mj
I need to check it live before trusting them. Last time their demo was very cherry pick though. Only time will tell about the quality.



45/70
@AntiZionist1917
I think Sora is also image generator. Maybe it's just frame of videos that are acting as image generation. But it has some form of image generation.



46/70
@yc3t_
holy



47/70
@D41Dev
I've been waiting to see text+video-to-video models, this is where significant leaps can be made.

- Full length movies can be made by inserting script snippets and a 1min clip of the previous scene. This can be done in a loop.

- Enhanced and simplified video editing



48/70
@seeupsidedown
LET. US. COOK.



49/70
@ShivOperator
Gradually, then suddenly



50/70
@GinChou
@HuoQubot



51/70
@AlexanderNL
haha hoefde je geen NDA te tekenen?



52/70
@emon_whatever
holy! another big bomb is about to drop



53/70
@AI_Car_Pool


[Quoted tweet]
Is it finally coming? @OpenAI

54/70
@bowtiedwhitebat
we bout to end the woke in movies



55/70
@Emily_Escapor
I am ready



56/70
@evren_mercan
Unlimited 2000 $/month



57/70
@SomBh1
Crazy. Imagine on a million GPU cluster. Can make a 15 min short movie.



58/70
@crypto_sam_974
who cares if it is not released...



59/70
@BreezeChai
Crazy



60/70
@_NamelessBrain_
Sora Turbo, not v2. Very different beasts.



61/70
@api_prlabs
Unlock the power of advanced AI with PR Labs' ChatGPT4 API! Starting at just $5/month with up to 2.4M requests,it's perfect for developers and businesses aiming to scale effortlessly.
Check now:ChatGPT 4
website: PR LABS API
/search?q=#ChatGPT4 /search?q=#OpenAI /search?q=#NewsAPI



62/70
@nextdao

63/70
@PrescienceDS
Exciting to see the Sora v2 release on the horizon! The addition of text-to-video and text+image-to-video features will definitely open up new creative possibilities. Can't wait to see how this will impact content creation and storytelling!



64/70
@YolaoDude
Looks great. But if the price tag is high, $200 or so, then i will jump in IF...
-It can generate FAR more than just 5 to 10 seconds videos!
-you can have full control of the movement of the characters, video to video.
-the character are consistent.



65/70
@aidesignss
sora v1 has not been released yet



66/70
@JogishE45866
Wonderful



67/70
@nextdao
http://OpenAI.chat → http://OpenAI.com

http://OpenAI.tech → http://OpenAI.com

http://OpenAI.tools→ http://OpenAI.com

Now only two domain names for sale.
@sama @OpenAI

openai.im is available for purchase - Sedo.com

openai.gg is available for purchase - Sedo.com

/search?q=#OpenAI



68/70
@Opic3D
Cool!



69/70
@farzadhss
Is it open source?



70/70
@irrealer
wild.




To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196

 

[Jesus H. Christ]

Anybody in here got access to Sora? I can't register as of now

 

[Jesus H. Christ]

 

[Stone Cold]

 

[newarkhiphop]

Anybody in here got access to Sora? I can't register as of now

I've had access since day 1

 

[bnew]

 

[bnew]

Spoiler: thread continued

Spoiler: full text & large images

1/11
@_philschmid
WTF?! New open-source physics AI engine absolutely insane! Genesis is a new physics engine that combines ultra-fast simulation with generative capabilities to create dynamic 4D worlds for robotics and physics.

TL;DR:
430,000x faster than real-time physics simulation, processes 43M FPS on a single RTX 4090
Built in pure Python, 10-80x faster than existing GPU solutions like Isaac Gym
Cross-platform support: Linux, MacOS, Windows, with CPU, NVIDIA, AMD, and Apple Metal backends
Unified framework combining multiple physics solvers: Rigid body, MPM, SPH, FEM, PBD, Stable Fluid
Extensive robot support: arms, legged robots, drones, soft robots; supports MJCF, URDF, obj, glb files
Built-in photorealistic ray-tracing rendering
Takes only 26 seconds to train real-world transferrable robot locomotion policies
Simple installation via pip: pip install genesis-world
Physics engine and simulation platform are fully open-sourced
”.generate” method/generative framework coming soon.



https://video.twimg.com/ext_tw_video/1869639134156840960/pu/vid/avc1/1280x720/rffXgweJaKVMxGFQ.mp4

2/11
@_philschmid
Code: GitHub - Genesis-Embodied-AI/Genesis: A generative world for general-purpose robotics & embodied AI learning.
Documentation: Genesis — Genesis 0.2.0 documentation

GitHub - Genesis-Embodied-AI/Genesis: A generative world for general-purpose robotics & embodied AI learning.



3/11
@ma5701458
@pikaso_me screenshot this



4/11
@pikaso_me
Enjoy your screenshot and...

Get 10 stickers for $1: $1 for 10 | Sticker Mule

5/11
@PamirSevincel
this is insane. you probably won't need that much real world data to train physical systems e.g. humanoid robots.

@adcock_brett what do you think?



6/11
@Mooie_89
@khouuba



7/11
@BalajiAkiri
A new era of Robotics begins



8/11
@360
Reality breaks more every day



9/11
@AIBuzzNews
@desy @desynews das könnte spannend und auch nützlich sein.



10/11
@glaksmono
This is super cool



11/11
@EducatingwithAI
Generative AI has hit a wall

In before: but this is not pure GenAI.

No, but it uses it with other tools - exactly what @ilyasut mentioned.

Spoiler: thread continued

Spoiler: full text & large images

1/11
@EHuanglu
This New AI Just Nuked the Competition

Genesis AI is here to wipe out every outdated simulation
and totally dominate AI world.

- Open sourced
- Create data from prompt
- 430,000x faster than real-time
- Create 4D physical worlds in seconds with text prompt

Let's dive in:



https://video.twimg.com/ext_tw_video/1869694710941618176/pu/vid/avc1/1280x720/dZ67k0pVaJpn20Ny.mp4

2/11
@EHuanglu
1. Generating 4D dynamical & physical world

• VLM-based generative agent
• Worlds provide diverse data modalities.
• Generates physically accurate, view consistent videos with camera and object motion.



https://video.twimg.com/ext_tw_video/1869709610762055682/pu/vid/avc1/1280x720/vznCJHqYHQh66u3C.mp4

3/11
@EHuanglu
2. Precise control

• Provides complete control over physics
• Handles camera motion and parameters with precision



https://video.twimg.com/ext_tw_video/1869709664302313472/pu/vid/avc1/1280x720/AnS2VyDilYPHlN2a.mp4

4/11
@EHuanglu
3. Character Motion Generation

• A Chinese soldier performs the Gangnam Style dance
• A Japanese samurai performs boxing
• A Roman soldier walks forward like a zombie



https://video.twimg.com/ext_tw_video/1869709732405182464/pu/vid/avc1/1280x720/tSN-btsf_6i4GXb_.mp4

5/11
@EHuanglu
4. Robotic Policy Generation

• Generative robotic agent + advanced physics engine
• Generates demonstration data for diverse skills
• Enables robots to learn and adapt autonomously.
• Powered by AI models for next-level automation.



https://video.twimg.com/ext_tw_video/1869709846528110592/pu/vid/avc1/1280x720/3fM-cF-Dmh5Ta9As.mp4

6/11
@EHuanglu
5. 3D & Fully Interactive Scene Generation

"A home interior scene with a living room (including a dinning space), a restroom, a study and a bedroom."



https://video.twimg.com/ext_tw_video/1869709919198515200/pu/vid/avc1/1280x720/frU1kO_8cGhMx4Fz.mp4

7/11
@EHuanglu
6. Speech Audio, Facial Animation & Emotion Generation



https://video.twimg.com/ext_tw_video/1869709968406142976/pu/vid/avc1/1280x720/LOXAphf2Ddtic8v1.mp4

8/11
@EHuanglu
Open sourced code:
GitHub - Genesis-Embodied-AI/Genesis: A generative world for general-purpose robotics & embodied AI learning.

Project Page:
Genesis



9/11
@EHuanglu
If you enjoyed reading this post,

Follow @EHuanglu for more great stuff!

And support with like/repost the post below

[Quoted tweet]
This New AI Just Nuked the Competition

Genesis AI is here to wipe out every outdated simulation
and totally dominate AI world.

- Open sourced
- Create data from prompt
- 430,000x faster than real-time
- Create 4D physical worlds in seconds with text prompt

Let's dive in:
[media=twitter]1869710532934254954[/media]

https://video.twimg.com/ext_tw_video/1869694710941618176/pu/vid/avc1/1280x720/dZ67k0pVaJpn20Ny.mp4

10/11
@zeng_wt
This is just 2024. Not even 2025. And we have this! wow



11/11
@EHuanglu
I always thought 2025 is the year of 3D, it seems I was short sighted

Spoiler: thread continued

Spoiler: full text & large images

1/11
@zhou_xian_
Everything you love about generative models — now powered by real physics!

Announcing the Genesis project — after a 24-month large-scale research collaboration involving over 20 research labs — a generative physics engine able to generate 4D dynamical worlds powered by a physics simulation platform designed for general-purpose robotics and physical AI applications.

Genesis's physics engine is developed in pure Python, while being 10-80x faster than existing GPU-accelerated stacks like Isaac Gym and MJX. It delivers a simulation speed ~430,000 faster than in real-time, and takes only 26 seconds to train a robotic locomotion policy transferrable to the real world on a single RTX4090 (see tutorial: Training Locomotion Policies with RL — Genesis 0.2.0 documentation).

The Genesis physics engine and simulation platform is fully open source at GitHub - Genesis-Embodied-AI/Genesis: A generative world for general-purpose robotics & embodied AI learning.. We'll gradually roll out access to our generative framework in the near future.

Genesis implements a unified simulation framework all from scratch, integrating a wide spectrum of state-of-the-art physics solvers, allowing simulation of the whole physical world in a virtual realm with the highest realism.

We aim to build a universal data engine that leverages an upper-level generative framework to autonomously create physical worlds, together with various modes of data, including environments, camera motions, robotic task proposals, reward functions, robot policies, character motions, fully interactive 3D scenes, open-world articulated assets, and more, aiming towards fully automated data generation for robotics, physical AI and other applications.

Open Source Code: GitHub - Genesis-Embodied-AI/Genesis: A generative world for general-purpose robotics & embodied AI learning.
Project webpage: Genesis

Documentation: Genesis — Genesis 0.2.0 documentation

1/n



https://video.twimg.com/ext_tw_video/1869510892880097280/pu/vid/avc1/1280x720/_dc5zlB1WmdE01Jh.mp4

2/11
@zhou_xian_
Nvidia brought GPU acceleration to robotic simulation, speeding up simulation speed by more than one order of magnitude compared to CPU-based simulation. This brought numerous amazing robotic skills to life by leveraging large-scale GPU-parallelized simulation. Genesis pushes up this speed by another order of magnitude. Note that the speed improvement is achieved with no compromise in simulation accuracy.
2/n



https://video.twimg.com/ext_tw_video/1869506856051261441/pu/vid/avc1/1280x720/F5sz3RnivNvuO6Dj.mp4

3/11
@zhou_xian_
Genesis supports simulating various types of physical phenomena. We developed from scratch a unified physics engine that integrates various SOTA physics solvers (MPM, SPH, FEM, Rigid Body, PBD, etc.), supporting simulation of a wide range of materials: rigid body, articulated body, Cloth, Liquid, Smoke, Deformables, Thin-shell materials, Elastic/Plastic Body, Robot Muscles, etc.

3/n



https://video.twimg.com/ext_tw_video/1869507363788541952/pu/vid/avc1/1280x720/NEU8FPHKy4Z_bAk6.mp4

4/11
@zhou_xian_
Genesis is the first-ever platform providing comprehensive support for soft muscles and soft robot and their interaction with rigid robots. Genesis also ships with a URDF-like soft-robot configuration system.

4/n



https://video.twimg.com/ext_tw_video/1869512601123594241/pu/vid/avc1/1280x720/UUrRbSSpOXEOIhY_.mp4

5/11
@zhou_xian_
Genesis's generative framework supports generating 3D and fully interactive scenes for training robotic skills
5/n



https://video.twimg.com/ext_tw_video/1869512781008973825/pu/vid/avc1/1280x720/62RDqV516piUnQM5.mp4

6/11
@zhou_xian_
Our generative agent autonomously proposes robotic tasks, design environments, write reward functions, and ultimately leading to automated generation of robotic policies.

6/n



https://video.twimg.com/ext_tw_video/1869512976299864064/pu/vid/avc1/1280x720/0YflDqvt8WnNtXNj.mp4

7/11
@zhou_xian_
Genesis's generative framework supports data generation beyond robotics, such as character motion:

7/n



https://video.twimg.com/ext_tw_video/1869513206672117760/pu/vid/avc1/1280x720/-sNINHa-_cgzgdiI.mp4

8/11
@zhou_xian_
Genesis's GPU parallellized IK solver is able to solve IK for 10,000 Franka arms simultaneously, under 2ms:

8/n



https://video.twimg.com/ext_tw_video/1869513330584338432/pu/vid/avc1/1280x720/JzGz03g2Il-_wzLD.mp4

9/11
@zhou_xian_
We support native non-convex collision handling:

9/n



https://video.twimg.com/ext_tw_video/1869513464055492608/pu/vid/avc1/1280x720/B6sCV4PMyOtFHggC.mp4

10/11
@zhou_xian_
Genesis supports a physically accurate tactile sensing simulation module: GitHub - Genesis-Embodied-AI/DiffTactile: [ICLR 2024] DiffTactile: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation. (Will be integrated into the main branch in a future release soon)

10/n



11/11
@zhou_xian_
Finally, a cute interactive physical Tetris game made with Genesis

Thanks to all the amazing collaborators who together made everything possible over the last two years! There's no space here to @ every single one, but a huge kudos to the whole Genesis team!

We welcome everyone from the open-source community to come join us and build Genesis with us together!

11/11



https://video.twimg.com/ext_tw_video/1869514325922058240/pu/vid/avc1/1280x720/kOCJbJ4KQnUJw1ht.mp4

 

[bnew]

Spoiler: thread continued

Spoiler: full text & large images

1/11
@AngryTomtweets
AI is unstoppable.

Kling AI 1.6 just completely changed the AI video game.

This is 100% AI

1. Snorlax



https://video.twimg.com/amplify_video/1870386402623700992/vid/avc1/1280x720/5fkrgqQdbqQjhtal.mp4

2/11
@AngryTomtweets
2. Monk and his giant warsteed traversing a river



https://video.twimg.com/ext_tw_video/1871074611997106176/pu/vid/avc1/1280x720/O76ym0wcod89avBU.mp4

3/11
@AngryTomtweets
3. Psyduck sleeping in the Colosseum



https://video.twimg.com/amplify_video/1871105665978322944/vid/avc1/1280x720/V9-JyzlBymLyD2Gj.mp4

4/11
@AngryTomtweets
4. Fury vs. Usyk 2 with @Kling_ai 1.6 Image-to-video



https://video.twimg.com/ext_tw_video/1871002017700741120/pu/vid/avc1/1286x720/2NQm8U_ygh0GEL51.mp4

5/11
@AngryTomtweets
5. Vibes



https://video.twimg.com/ext_tw_video/1870490417739030528/pu/vid/avc1/1280x720/Fot-ki-Olrgw9U27.mp4

6/11
@AngryTomtweets
6. Hyper speed POV camera in Kling 1.6



https://video.twimg.com/ext_tw_video/1870572212387713024/pu/vid/avc1/1280x720/vVD8yzrtpjh31ntU.mp4

7/11
@AngryTomtweets
7. Mystic Super real model + Kling 1.6



https://video.twimg.com/ext_tw_video/1869073663107969024/pu/vid/avc1/1920x1080/XVEUcHPEfembiRYj.mp4

8/11
@AngryTomtweets
8. Facial expressions with Kling 1.6



https://video.twimg.com/ext_tw_video/1871273133027581952/pu/vid/avc1/1280x720/xUEfO5TJf50jNK_g.mp4

9/11
@AngryTomtweets
9. Neon Samurai Awakens



https://video.twimg.com/ext_tw_video/1871228834722263040/pu/vid/avc1/1280x720/Q0XNU3c0lOgjiBOj.mp4

10/11
@AngryTomtweets
10. Santa has invited the Grinch over for a nice Christmas dinner



https://video.twimg.com/ext_tw_video/1871255849684893696/pu/vid/avc1/1920x1080/vnoU5wuGDQgVOCj-.mp4

11/11
@AngryTomtweets
That's a wrap!

If you enjoyed this thread:

1. Follow me @AngryTomtweets for more of these
2. RT the tweet below to share this thread with your audience

[Quoted tweet]
AI is unstoppable.

Kling AI 1.6 just completely changed the AI video game.

This is 100% AI

1. Snorlax


https://video.twimg.com/amplify_video/1870386402623700992/vid/avc1/1280x720/5fkrgqQdbqQjhtal.mp4


To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196

Spoiler: thread continued

Spoiler: full text & large images

1/11
@JayKay65220066
Top Hat's Christmas Ascent Up Cookie Tree

Made with
@Kling_ai New 1.6

/search?q=#AIart Good Tuesday /search?q=#Tuesdaymotivation /search?q=#Tuesdayvibes



https://video.twimg.com/ext_tw_video/1871493334159466496/pu/vid/avc1/1920x1080/kX83ytpLV08ggEJN.mp4

2/11
@ASanswers
This is Fantastic!! Merry Christmas Eve!!



3/11
@JayKay65220066
Merry Christmas Eve!!



4/11
@GuidedbyHumans
This is awesome



5/11
@JayKay65220066
Ty



6/11
@amazingyearT1
So creative and charming!



7/11
@JayKay65220066
Ty



8/11
@DJPetra2
Nice!



9/11
@JayKay65220066
Ty



10/11
@Ankit_patel211
awesome animation jay!



11/11
@JayKay65220066
Ty




To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196

Spoiler: thread continued

Spoiler: full text & large images

1/11
@mxvdxn
Exploring a hybrid of indie rock music video and travel vlog style using @Kling_ai new 1.6 model.

→ text2img: Midjourney V6.1
→ img2vid: @Kling_ai
→ Music: @udiomusic

Video prompt:
vlog documentary style, candid, natural acting



https://video.twimg.com/ext_tw_video/1871543862927437824/pu/vid/avc1/1280x720/Ll20alKaXWBYsmA9.mp4

2/11
@mxvdxn
This one is probably my favorite. You know those little moments when you record your loved one, and they suddenly get soooo cute and embarrassed, trying to cover the camera?

I truly love the result.

For this shot, I used this video prompt:
vlog documentary style, captures a playful and candid moment as the woman approaches the camera with a warm smile, slightly embarrassed, gently reaching out to cover the lens with her hand.

3/11
@HBCoop_
Great idea to blend these styles and the result looks fantastic



4/11
@mxvdxn
Thanks Heather I've been enjoying this style a lot. Love how natural it looks.



5/11
@cengizkaracik
Great work



6/11
@mxvdxn
Much appreciated Thank you so much



7/11
@arsenisan
Indeed, quite natural. Well done



8/11
@mxvdxn
Thank you so much



9/11
@U79916881747113
The asthetics touches ur soul as it reminds me of the mountains, the kids, the flag blowing in wind, the market, every part of the video is a dejavu remembering my heartland my country Nepal, even though nothing is perfect some differ



10/11
@mxvdxn
Thank you so much for your words And yes, I truly was very influenced by Nepal. I've never been there, I've only seen it in documentaries. Definitely a place I want to visit. I apologize if there's less accuracy in it, but I guess this is what makes AI really interesting. It kind of brings these dreams and fantasies to life, allowing us to travel to a place like your hometown.



11/11
@Eric520CC
COOL




To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196

Spoiler: thread continued

Spoiler: full text & large images

1/11
@StevieMac03
Monk and his giant warsteed traversing a river. Kling 1.6 image to video.




https://video.twimg.com/ext_tw_video/1871074611997106176/pu/vid/avc1/1280x720/O76ym0wcod89avBU.mp4

2/11
@jamesyeung18
This series is awesome!



3/11
@StevieMac03
Thanks James I am overwhelmed with the interest in these and humbled



4/11
@ShelbyExchange
Wow epic.



5/11
@StevieMac03
Cheers



6/11
@lafuturvision
The question might seem intrusive, but could you tell us how many credits you used to create a sequence like this?



7/11
@StevieMac03
It's fine. There were no discarded shots here, but I know Kling really well, in the previous clip I had one misfire where the steed started bucking as if trying to throw the rider when a rock popped up in the river. It's consistency is very good. Sometimes I'll run two generations and choose the best, but I have found with 1.6 that either would be useable.



8/11
@AuroraArabel
Amazing !!!



9/11
@StevieMac03
Thank you Aurora



10/11
@16izayoi32
What is the original image made from what generative AI?



11/11
@StevieMac03
Midjourney




To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196

 

[bnew]

 

[CopiousX]

What I don't understand is why the American models all have six or 10 fingers on a hand, while the Chinese versions seem to have normal human handed people.



Don't we have the highest paid , smartest people in the world based in that area that that open AI is in? How did China crack the code? Is their version fake?

 

[Mowgli]

shyt still look like it's moving in reverse

 

[bnew]

 

[bnew]

https://archive.is/ZpgPy

Spoiler: full text & large images

1/2
@laszlogaal_
Next test with /search?q=#Veo2 : Food packshot/videography.



https://video.twimg.com/ext_tw_video/1874756925952536576/pu/vid/avc1/1920x1080/RAe7YsLIoO8hw7uy.mp4

2/2
@CameronHolmes92
Amazing how (mostly) passable the physics is here




To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196

Spoiler: full text & large images

1/4
@laszlogaal_
If you needed one reason to love /search?q=#Veo2 , I will give you 100. This is the most diverse test I did to any model so far, more than 100 very different - and hard! - scenes that will go into my prompt library collection that I’m building these days



https://video.twimg.com/ext_tw_video/1873676247999631360/pu/vid/avc1/1920x1080/bEByXXFfvMm1Mc_r.mp4

2/4
@JesusPlazaX
Amazing. As a director I would love this as my Reel.
All prompting is in English? Text to video? Can you use this for commercial usage???



3/4
@JesusPlazaX




4/4
@JH4TC
great demo!




To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196

Spoiler: full text & large images

1/1
@laszlogaal_
Light testing with, all text-to-video /search?q=#Veo2 /search?q=#VideoFX

more information: Sign Up | LinkedIn



https://video.twimg.com/ext_tw_video/1872260846300332032/pu/vid/avc1/1920x1080/mKacxPnglMDaBro2.mp4


To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196

 

[bnew]

Spoiler: thread continued

Spoiler: full text & large images

1/8
@emollick
Creating fictional Game of the Year YouTube videos with Veo 2 kind of illustrates how similar a lot of games have become that the random AI-generated game clips seem so plausible. (This is entirely AI generated from a text prompt)



https://video.twimg.com/ext_tw_video/1874645548268994560/pu/vid/avc1/1280x720/pqConir6WeqJDaeU.mp4

2/8
@emollick
And who can forget these games.



https://video.twimg.com/ext_tw_video/1874646194577649664/pu/vid/avc1/1280x720/XIWJgLTBMdJV_CaC.mp4

3/8
@axel_pond
my brother in Christ the models were trained on modern games



4/8
@emollick
Yes, which was my point.



5/8
@AILeaksAndNews
Very impressive



6/8
@KuittinenPetri
Past 5 years have been pretty pathetic when it comes big main stream games. There hasn't been a single really big hit, which is both original and sold at least $1+ billion worth of.

Here are some big hits, but they were all released more than 5 years ago:
League of Legends (2009)
Minecraft (2011)
GTA V (2013)
PlayerUnknown’s Battlegrounds (2017)
Fortnite (2017)

Instead in past 5 years we have seen massive amount of sequels, spin-offs, and copycats.

And we have seen massive flops e.g. Concord (Firewalk Studios/Sony 2024). The Game cost $400 million and it was pulled offline just 2 weeks from its release, because of lack of player interest! The game had no originality and one of the worst character designs of its genre (I had to use it as negative example during my game design classes).

Hollywood has been in similar apathetic state since 2020. Tons of films and TV series which look and sound the same, have mediocre plot, cringe-level dialogue, mediocre acting, massive budgets and big box office bombs.



7/8
@davecraige
that's wild



8/8
@saulosouzaw
I didn't realize at first the guy was also generated




To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196

Spoiler: full text & large images

1/11
@emollick
Sora: "stereotypical montage of flashback shots of the dead wife of the hero, talking to the camera, except she is holding a potato in every scene"



https://video.twimg.com/ext_tw_video/1874958530655948800/pu/vid/avc1/1280x720/YBDO23NR81lET5hX.mp4

2/11
@whosEFM
Almost got me.

I know John Wick 5 leaked footage when I see it



3/11
@NFTherder
Compute well spend



4/11
@Court_Reinland
Haha omg



5/11
@Przegaa
macabre



6/11
@GentJayson
Still sad



7/11
@odious_influx
Let me know when it can do conjoined twins eating spaghetti.



8/11
@SamWalker100
Needs the close up sideways shot in bed when she just woke up with a sunbeam behind.



9/11
@CommonSenseMars
"Every spud reminds me of him and what he sacrificed."



https://video.twimg.com/ext_tw_video/1874959777501171713/pu/vid/avc1/854x480/c7n4AwwQqUczmuj6.mp4

10/11
@AddisonGillis
Sammy didn't have a wife! It was your wife that had a potato.



11/11
@MaximumRes
Coming to theaters this fall: Mr. Potatohead, Vengeance is a-peal-ing. When one spud is out for revenge, evil plays a game of hot potato it can only loose.
From Sony pictures.




To post tweets in this format, more info here: https://www.thecoli.com/threads/tips-and-tricks-for-posting-the-coli-megathread.984734/post-52211196